Axiomatic design of a goal-agnostic AI objective that aggregates human power across goals, people, time, and uncertainty.
Bayesian theory of mind: Modeling joint belief-desire attribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences
Axiomatic design of a goal-agnostic AI objective that aggregates human power across goals, people, time, and uncertainty.